Training speed decreases

[huixiancheng]

I used it on semantic segmentation and found that the loss convergence speed is very very slow(compare with other backbone)

[EEWenbinWu]

I used it on pose estimation and I have the same problem.

[huixiancheng]

maybe it's cause by depthwise convolution

[nsapkota417]

I used it on semantic segmentation and found that the loss convergence speed is very very slow(compare with other backbone)

Hi, what was your segmentation performance like? Were you trying on Cityscape dataset?

[huixiancheng]

No. Finally I give up.